From 7cc8883074b040aa8c1ebd3a17463b0ea3a9ef16 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Tue, 13 May 2008 16:29:20 +0300
Subject: KVM: Remove decache_vcpus_on_cpu() and related callbacks

Obsoleted by the vmx-specific per-cpu list.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 include/linux/kvm_host.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux/kvm_host.h')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index de9d1df4bba2..865dcbcb891f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -135,9 +135,6 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 void vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
-void decache_vcpus_on_cpu(int cpu);
-
-
 int kvm_init(void *opaque, unsigned int vcpu_size,
 		  struct module *module);
 void kvm_exit(void);
-- 
cgit v1.2.3


From 92760499d01ef91518119908eb9b8798b6c9bd3f Mon Sep 17 00:00:00 2001
From: Laurent Vivier <Laurent.Vivier@bull.net>
Date: Fri, 30 May 2008 16:05:53 +0200
Subject: KVM: kvm_io_device: extend in_range() to manage len and write
 attribute

Modify member in_range() of structure kvm_io_device to pass length and the type
of the I/O (write or read).

This modification allows to use kvm_io_device with coalesced MMIO.

Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/ia64/kvm/kvm-ia64.c |  6 +++---
 arch/x86/kvm/i8254.c     |  6 ++++--
 arch/x86/kvm/i8259.c     |  3 ++-
 arch/x86/kvm/lapic.c     |  3 ++-
 arch/x86/kvm/x86.c       | 28 +++++++++++++++++-----------
 include/linux/kvm_host.h |  3 ++-
 virt/kvm/ioapic.c        |  3 ++-
 virt/kvm/iodev.h         |  8 +++++---
 virt/kvm/kvm_main.c      |  5 +++--
 9 files changed, 40 insertions(+), 25 deletions(-)

(limited to 'include/linux/kvm_host.h')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 7c504be57972..bb58df7cc418 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -195,11 +195,11 @@ int kvm_dev_ioctl_check_extension(long ext)
 }
 
 static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
-					gpa_t addr)
+					gpa_t addr, int len, int is_write)
 {
 	struct kvm_io_device *dev;
 
-	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len, is_write);
 
 	return dev;
 }
@@ -231,7 +231,7 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->exit_reason = KVM_EXIT_MMIO;
 	return 0;
 mmio:
-	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr);
+	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr, p->size, !p->dir);
 	if (mmio_dev) {
 		if (!p->dir)
 			kvm_iodevice_write(mmio_dev, p->addr, p->size,
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 60074dc66bd7..9e3391e9a1b7 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -460,7 +460,8 @@ static void pit_ioport_read(struct kvm_io_device *this,
 	mutex_unlock(&pit_state->lock);
 }
 
-static int pit_in_range(struct kvm_io_device *this, gpa_t addr)
+static int pit_in_range(struct kvm_io_device *this, gpa_t addr,
+			int len, int is_write)
 {
 	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
 		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
@@ -501,7 +502,8 @@ static void speaker_ioport_read(struct kvm_io_device *this,
 	mutex_unlock(&pit_state->lock);
 }
 
-static int speaker_in_range(struct kvm_io_device *this, gpa_t addr)
+static int speaker_in_range(struct kvm_io_device *this, gpa_t addr,
+			    int len, int is_write)
 {
 	return (addr == KVM_SPEAKER_BASE_ADDRESS);
 }
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index ab29cf2def47..5857f59ad4aa 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -346,7 +346,8 @@ static u32 elcr_ioport_read(void *opaque, u32 addr1)
 	return s->elcr;
 }
 
-static int picdev_in_range(struct kvm_io_device *this, gpa_t addr)
+static int picdev_in_range(struct kvm_io_device *this, gpa_t addr,
+			   int len, int is_write)
 {
 	switch (addr) {
 	case 0x20:
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e48d19394031..180ba7316da5 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -785,7 +785,8 @@ static void apic_mmio_write(struct kvm_io_device *this,
 
 }
 
-static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr)
+static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr,
+			   int len, int size)
 {
 	struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
 	int ret = 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4c94fad7f01e..ab3f5552d694 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1797,13 +1797,14 @@ static void kvm_init_msr_list(void)
  * Only apic need an MMIO device hook, so shortcut now..
  */
 static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu,
-						gpa_t addr)
+						gpa_t addr, int len,
+						int is_write)
 {
 	struct kvm_io_device *dev;
 
 	if (vcpu->arch.apic) {
 		dev = &vcpu->arch.apic->dev;
-		if (dev->in_range(dev, addr))
+		if (dev->in_range(dev, addr, len, is_write))
 			return dev;
 	}
 	return NULL;
@@ -1811,13 +1812,15 @@ static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu,
 
 
 static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
-						gpa_t addr)
+						gpa_t addr, int len,
+						int is_write)
 {
 	struct kvm_io_device *dev;
 
-	dev = vcpu_find_pervcpu_dev(vcpu, addr);
+	dev = vcpu_find_pervcpu_dev(vcpu, addr, len, is_write);
 	if (dev == NULL)
-		dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+		dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len,
+					  is_write);
 	return dev;
 }
 
@@ -1885,7 +1888,7 @@ mmio:
 	 * Is this MMIO handled locally?
 	 */
 	mutex_lock(&vcpu->kvm->lock);
-	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
+	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 0);
 	if (mmio_dev) {
 		kvm_iodevice_read(mmio_dev, gpa, bytes, val);
 		mutex_unlock(&vcpu->kvm->lock);
@@ -1940,7 +1943,7 @@ mmio:
 	 * Is this MMIO handled locally?
 	 */
 	mutex_lock(&vcpu->kvm->lock);
-	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
+	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 1);
 	if (mmio_dev) {
 		kvm_iodevice_write(mmio_dev, gpa, bytes, val);
 		mutex_unlock(&vcpu->kvm->lock);
@@ -2317,9 +2320,10 @@ static void pio_string_write(struct kvm_io_device *pio_dev,
 }
 
 static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu,
-					       gpa_t addr)
+					       gpa_t addr, int len,
+					       int is_write)
 {
-	return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr);
+	return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr, len, is_write);
 }
 
 int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
@@ -2351,7 +2355,7 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 
 	kvm_x86_ops->skip_emulated_instruction(vcpu);
 
-	pio_dev = vcpu_find_pio_dev(vcpu, port);
+	pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in);
 	if (pio_dev) {
 		kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data);
 		complete_pio(vcpu);
@@ -2433,7 +2437,9 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 		}
 	}
 
-	pio_dev = vcpu_find_pio_dev(vcpu, port);
+	pio_dev = vcpu_find_pio_dev(vcpu, port,
+				    vcpu->arch.pio.cur_count,
+				    !vcpu->arch.pio.in);
 	if (!vcpu->arch.pio.in) {
 		/* string PIO write */
 		ret = pio_copy_data(vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 865dcbcb891f..499ff0604234 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -52,7 +52,8 @@ struct kvm_io_bus {
 
 void kvm_io_bus_init(struct kvm_io_bus *bus);
 void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr);
+struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
+					  gpa_t addr, int len, int is_write);
 void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
 			     struct kvm_io_device *dev);
 
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index d0c668c6959e..c0d22870ee9c 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -307,7 +307,8 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector)
 			__kvm_ioapic_update_eoi(ioapic, i);
 }
 
-static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr)
+static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr,
+			   int len, int is_write)
 {
 	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
 
diff --git a/virt/kvm/iodev.h b/virt/kvm/iodev.h
index c14e642027b2..55e8846ac3a6 100644
--- a/virt/kvm/iodev.h
+++ b/virt/kvm/iodev.h
@@ -27,7 +27,8 @@ struct kvm_io_device {
 		      gpa_t addr,
 		      int len,
 		      const void *val);
-	int (*in_range)(struct kvm_io_device *this, gpa_t addr);
+	int (*in_range)(struct kvm_io_device *this, gpa_t addr, int len,
+			int is_write);
 	void (*destructor)(struct kvm_io_device *this);
 
 	void             *private;
@@ -49,9 +50,10 @@ static inline void kvm_iodevice_write(struct kvm_io_device *dev,
 	dev->write(dev, addr, len, val);
 }
 
-static inline int kvm_iodevice_inrange(struct kvm_io_device *dev, gpa_t addr)
+static inline int kvm_iodevice_inrange(struct kvm_io_device *dev,
+				       gpa_t addr, int len, int is_write)
 {
-	return dev->in_range(dev, addr);
+	return dev->in_range(dev, addr, len, is_write);
 }
 
 static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 83a0e5ce6037..9330fad2b918 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1350,14 +1350,15 @@ void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 	}
 }
 
-struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr)
+struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
+					  gpa_t addr, int len, int is_write)
 {
 	int i;
 
 	for (i = 0; i < bus->dev_count; i++) {
 		struct kvm_io_device *pos = bus->devs[i];
 
-		if (pos->in_range(pos, addr))
+		if (pos->in_range(pos, addr, len, is_write))
 			return pos;
 	}
 
-- 
cgit v1.2.3


From 5f94c1741bdc7a336553122036e8a779e616ccbf Mon Sep 17 00:00:00 2001
From: Laurent Vivier <Laurent.Vivier@bull.net>
Date: Fri, 30 May 2008 16:05:54 +0200
Subject: KVM: Add coalesced MMIO support (common part)

This patch adds all needed structures to coalesce MMIOs.
Until an architecture uses it, it is not compiled.

Coalesced MMIO introduces two ioctl() to define where are the MMIO zones that
can be coalesced:

- KVM_REGISTER_COALESCED_MMIO registers a coalesced MMIO zone.
  It requests one parameter (struct kvm_coalesced_mmio_zone) which defines
  a memory area where MMIOs can be coalesced until the next switch to
  user space. The maximum number of MMIO zones is KVM_COALESCED_MMIO_ZONE_MAX.

- KVM_UNREGISTER_COALESCED_MMIO cancels all registered zones inside
  the given bounds (bounds are also given by struct kvm_coalesced_mmio_zone).

The userspace client can check kernel coalesced MMIO availability by asking
ioctl(KVM_CHECK_EXTENSION) for the KVM_CAP_COALESCED_MMIO capability.
The ioctl() call to KVM_CAP_COALESCED_MMIO will return 0 if not supported,
or the page offset where will be stored the ring buffer.
The page offset depends on the architecture.

After an ioctl(KVM_RUN), the first page of the KVM memory mapped points to
a kvm_run structure. The offset given by KVM_CAP_COALESCED_MMIO is
an offset to the coalesced MMIO ring expressed in PAGE_SIZE relatively
to the address of the start of th kvm_run structure. The MMIO ring buffer
is defined by the structure kvm_coalesced_mmio_ring.

[akio: fix oops during guest shutdown]

Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 include/linux/kvm.h       |  29 +++++++++
 include/linux/kvm_host.h  |   4 ++
 virt/kvm/coalesced_mmio.c | 156 ++++++++++++++++++++++++++++++++++++++++++++++
 virt/kvm/coalesced_mmio.h |  23 +++++++
 virt/kvm/kvm_main.c       |  57 +++++++++++++++++
 5 files changed, 269 insertions(+)
 create mode 100644 virt/kvm/coalesced_mmio.c
 create mode 100644 virt/kvm/coalesced_mmio.h

(limited to 'include/linux/kvm_host.h')

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index a281afeddfbb..1c908ac29c6c 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -173,6 +173,30 @@ struct kvm_run {
 	};
 };
 
+/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
+
+struct kvm_coalesced_mmio_zone {
+	__u64 addr;
+	__u32 size;
+	__u32 pad;
+};
+
+struct kvm_coalesced_mmio {
+	__u64 phys_addr;
+	__u32 len;
+	__u32 pad;
+	__u8  data[8];
+};
+
+struct kvm_coalesced_mmio_ring {
+	__u32 first, last;
+	struct kvm_coalesced_mmio coalesced_mmio[0];
+};
+
+#define KVM_COALESCED_MMIO_MAX \
+	((PAGE_SIZE - sizeof(struct kvm_coalesced_mmio_ring)) / \
+	 sizeof(struct kvm_coalesced_mmio))
+
 /* for KVM_TRANSLATE */
 struct kvm_translation {
 	/* in */
@@ -346,6 +370,7 @@ struct kvm_trace_rec {
 #define KVM_CAP_NOP_IO_DELAY 12
 #define KVM_CAP_PV_MMU 13
 #define KVM_CAP_MP_STATE 14
+#define KVM_CAP_COALESCED_MMIO 15
 
 /*
  * ioctls for VM fds
@@ -371,6 +396,10 @@ struct kvm_trace_rec {
 #define KVM_CREATE_PIT		  _IO(KVMIO,  0x64)
 #define KVM_GET_PIT		  _IOWR(KVMIO, 0x65, struct kvm_pit_state)
 #define KVM_SET_PIT		  _IOR(KVMIO,  0x66, struct kvm_pit_state)
+#define KVM_REGISTER_COALESCED_MMIO \
+			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
+#define KVM_UNREGISTER_COALESCED_MMIO \
+			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
 
 /*
  * ioctls for vcpu fds
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 499ff0604234..d220b4926c4a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -117,6 +117,10 @@ struct kvm {
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	atomic_t users_count;
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	struct kvm_coalesced_mmio_dev *coalesced_mmio_dev;
+	struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
+#endif
 };
 
 /* The guest did something we don't support. */
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
new file mode 100644
index 000000000000..5ae620d32fac
--- /dev/null
+++ b/virt/kvm/coalesced_mmio.c
@@ -0,0 +1,156 @@
+/*
+ * KVM coalesced MMIO
+ *
+ * Copyright (c) 2008 Bull S.A.S.
+ *
+ *  Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ *
+ */
+
+#include "iodev.h"
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+
+#include "coalesced_mmio.h"
+
+static int coalesced_mmio_in_range(struct kvm_io_device *this,
+				   gpa_t addr, int len, int is_write)
+{
+	struct kvm_coalesced_mmio_dev *dev =
+				(struct kvm_coalesced_mmio_dev*)this->private;
+	struct kvm_coalesced_mmio_zone *zone;
+	int next;
+	int i;
+
+	if (!is_write)
+		return 0;
+
+	/* kvm->lock is taken by the caller and must be not released before
+         * dev.read/write
+         */
+
+	/* Are we able to batch it ? */
+
+	/* last is the first free entry
+	 * check if we don't meet the first used entry
+	 * there is always one unused entry in the buffer
+	 */
+
+	next = (dev->kvm->coalesced_mmio_ring->last + 1) %
+							KVM_COALESCED_MMIO_MAX;
+	if (next == dev->kvm->coalesced_mmio_ring->first) {
+		/* full */
+		return 0;
+	}
+
+	/* is it in a batchable area ? */
+
+	for (i = 0; i < dev->nb_zones; i++) {
+		zone = &dev->zone[i];
+
+		/* (addr,len) is fully included in
+		 * (zone->addr, zone->size)
+		 */
+
+		if (zone->addr <= addr &&
+		    addr + len <= zone->addr + zone->size)
+			return 1;
+	}
+	return 0;
+}
+
+static void coalesced_mmio_write(struct kvm_io_device *this,
+				 gpa_t addr, int len, const void *val)
+{
+	struct kvm_coalesced_mmio_dev *dev =
+				(struct kvm_coalesced_mmio_dev*)this->private;
+	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
+
+	/* kvm->lock must be taken by caller before call to in_range()*/
+
+	/* copy data in first free entry of the ring */
+
+	ring->coalesced_mmio[ring->last].phys_addr = addr;
+	ring->coalesced_mmio[ring->last].len = len;
+	memcpy(ring->coalesced_mmio[ring->last].data, val, len);
+	smp_wmb();
+	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
+}
+
+static void coalesced_mmio_destructor(struct kvm_io_device *this)
+{
+	kfree(this);
+}
+
+int kvm_coalesced_mmio_init(struct kvm *kvm)
+{
+	struct kvm_coalesced_mmio_dev *dev;
+
+	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	dev->dev.write  = coalesced_mmio_write;
+	dev->dev.in_range  = coalesced_mmio_in_range;
+	dev->dev.destructor  = coalesced_mmio_destructor;
+	dev->dev.private  = dev;
+	dev->kvm = kvm;
+	kvm->coalesced_mmio_dev = dev;
+	kvm_io_bus_register_dev(&kvm->mmio_bus, &dev->dev);
+
+	return 0;
+}
+
+int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
+				         struct kvm_coalesced_mmio_zone *zone)
+{
+	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;
+
+	if (dev == NULL)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
+		mutex_unlock(&kvm->lock);
+		return -ENOBUFS;
+	}
+
+	dev->zone[dev->nb_zones] = *zone;
+	dev->nb_zones++;
+
+	mutex_unlock(&kvm->lock);
+	return 0;
+}
+
+int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
+					   struct kvm_coalesced_mmio_zone *zone)
+{
+	int i;
+	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;
+	struct kvm_coalesced_mmio_zone *z;
+
+	if (dev == NULL)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	i = dev->nb_zones;
+	while(i) {
+		z = &dev->zone[i - 1];
+
+		/* unregister all zones
+		 * included in (zone->addr, zone->size)
+		 */
+
+		if (zone->addr <= z->addr &&
+		    z->addr + z->size <= zone->addr + zone->size) {
+			dev->nb_zones--;
+			*z = dev->zone[dev->nb_zones];
+		}
+		i--;
+	}
+
+	mutex_unlock(&kvm->lock);
+
+	return 0;
+}
diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h
new file mode 100644
index 000000000000..5ac0ec628461
--- /dev/null
+++ b/virt/kvm/coalesced_mmio.h
@@ -0,0 +1,23 @@
+/*
+ * KVM coalesced MMIO
+ *
+ * Copyright (c) 2008 Bull S.A.S.
+ *
+ *  Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ *
+ */
+
+#define KVM_COALESCED_MMIO_ZONE_MAX 100
+
+struct kvm_coalesced_mmio_dev {
+	struct kvm_io_device dev;
+	struct kvm *kvm;
+	int nb_zones;
+	struct kvm_coalesced_mmio_zone zone[KVM_COALESCED_MMIO_ZONE_MAX];
+};
+
+int kvm_coalesced_mmio_init(struct kvm *kvm);
+int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
+                                       struct kvm_coalesced_mmio_zone *zone);
+int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
+                                         struct kvm_coalesced_mmio_zone *zone);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9330fad2b918..7d10dfa0d388 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -47,6 +47,10 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#include "coalesced_mmio.h"
+#endif
+
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
@@ -185,10 +189,23 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);
 static struct kvm *kvm_create_vm(void)
 {
 	struct kvm *kvm = kvm_arch_create_vm();
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	struct page *page;
+#endif
 
 	if (IS_ERR(kvm))
 		goto out;
 
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page) {
+		kfree(kvm);
+		return ERR_PTR(-ENOMEM);
+	}
+	kvm->coalesced_mmio_ring =
+			(struct kvm_coalesced_mmio_ring *)page_address(page);
+#endif
+
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
 	spin_lock_init(&kvm->mmu_lock);
@@ -200,6 +217,9 @@ static struct kvm *kvm_create_vm(void)
 	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	kvm_coalesced_mmio_init(kvm);
+#endif
 out:
 	return kvm;
 }
@@ -242,6 +262,10 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	spin_unlock(&kvm_lock);
 	kvm_io_bus_destroy(&kvm->pio_bus);
 	kvm_io_bus_destroy(&kvm->mmio_bus);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	if (kvm->coalesced_mmio_ring != NULL)
+		free_page((unsigned long)kvm->coalesced_mmio_ring);
+#endif
 	kvm_arch_destroy_vm(kvm);
 	mmdrop(mm);
 }
@@ -825,6 +849,10 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 #ifdef CONFIG_X86
 	else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->arch.pio_data);
+#endif
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
+		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
 	else
 		return VM_FAULT_SIGBUS;
@@ -1148,6 +1176,32 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		break;
 	}
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	case KVM_REGISTER_COALESCED_MMIO: {
+		struct kvm_coalesced_mmio_zone zone;
+		r = -EFAULT;
+		if (copy_from_user(&zone, argp, sizeof zone))
+			goto out;
+		r = -ENXIO;
+		r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_UNREGISTER_COALESCED_MMIO: {
+		struct kvm_coalesced_mmio_zone zone;
+		r = -EFAULT;
+		if (copy_from_user(&zone, argp, sizeof zone))
+			goto out;
+		r = -ENXIO;
+		r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -1231,6 +1285,9 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = PAGE_SIZE;     /* struct kvm_run */
 #ifdef CONFIG_X86
 		r += PAGE_SIZE;    /* pio data page */
+#endif
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
 	case KVM_TRACE_ENABLE:
-- 
cgit v1.2.3


From 34d4cb8fca1f2a31be152b74797e6cd160ec9de6 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Thu, 10 Jul 2008 20:49:31 -0300
Subject: KVM: MMU: nuke shadowed pgtable pages and ptes on memslot destruction

Flush the shadow mmu before removing regions to avoid stale entries.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/ia64/kvm/kvm-ia64.c   | 3 +++
 arch/powerpc/kvm/powerpc.c | 4 ++++
 arch/s390/kvm/kvm-s390.c   | 4 ++++
 arch/x86/kvm/x86.c         | 5 +++++
 include/linux/kvm_host.h   | 1 +
 virt/kvm/kvm_main.c        | 3 +++
 6 files changed, 20 insertions(+)

(limited to 'include/linux/kvm_host.h')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 9408b30576d6..2672f4d278ac 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1455,6 +1455,9 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
 
 long kvm_arch_dev_ioctl(struct file *filp,
 		unsigned int ioctl, unsigned long arg)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b850d2497027..53826a5f6c06 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -170,6 +170,10 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
+
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 399acf3f64dd..1782cbcd2829 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -675,6 +675,10 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
+
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b131f3c0cf64..9f1cdb011cff 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4032,6 +4032,11 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+	kvm_mmu_zap_all(kvm);
+}
+
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d220b4926c4a..07d68a8ae8e9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -168,6 +168,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
+void kvm_arch_flush_shadow(struct kvm *kvm);
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9ccaf8f5402e..30b36368fcdf 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -405,6 +405,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (mem->slot >= kvm->nmemslots)
 		kvm->nmemslots = mem->slot + 1;
 
+	if (!npages)
+		kvm_arch_flush_shadow(kvm);
+
 	*memslot = new;
 
 	r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc);
-- 
cgit v1.2.3